Combining signals includes receiving signals from communication devices, where each signal is associated with a content describing the signal. The following is repeated for each signal: the content associated with a signal is examined, whether the signal is a voice signal is determined in accordance with the content, and the signals are sent to a signal combiner in accordance with the determination of whether the signal is a voice signal. The signals are combined at the signal combiner.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for combining a plurality of signals, comprising: receiving a plurality of signals from a plurality of communication devices, each signal received from a communication device, each signal associated with a content describing the signal; repeating the following for each signal of the plurality of signals: examining the content associated with a signal; determining whether the signal comprises a voice signal in accordance with the content; and sending the signal to a signal combiner in accordance with the determination of whether the signal comprises a voice signal by assigning a higher weight to the signal if the signal comprises a voice signal, assigning a lower weight to the signal if the signal comprises another type of signal, and sending the signal to the signal combiner in accordance to the assignment; and combining the signals at the signal combiner.
2. The method of claim 1 , wherein determining whether the signal comprises a voice signal in accordance with the content comprises: generating a feature vector for the signal, the feature vector describing the content associated with the signal; comparing the feature vector to a voice signal vector describing a typical voice signal; and determining whether the signal comprises a voice signal in accordance with the comparison.
3. The method of claim 1 , wherein determining whether the signal comprises a voice signal in accordance with the content comprises: identifying a frequency spectrum associated with the signal; and determining whether the signal comprises a voice signal in accordance with the frequency spectrum.
4. The method of claim 1 , wherein determining whether the signal comprises a voice signal in accordance with the content comprises determining whether the signal comprises a voice signal in accordance with the content at a speech recognition module.
5. The method of claim 1 , wherein sending the signals to the signal combiner in accordance with the determination of whether the signal comprises a voice signal comprises: sending the signal to the signal combiner if the signal comprises a voice signal; and blocking the signal if the signal comprises another type of signal.
6. Logic for combining a plurality of signals, the logic embodied in a medium and operable to: receive a plurality of signals from a plurality of communication devices, each signal received from a communication device, each signal associated with a content describing the signal; repeat the following for each signal of the plurality of signals: examine the content associated with a signal; determine whether the signal comprises a voice signal in accordance with the content; and send the signal to a signal combiner in accordance with the determination of whether the signal comprises a voice signal by assigning a higher weight to the signal if the signal comprises a voice signal, assigning a lower weight to the signal if the signal comprises another type of signal, and sending the signal to the signal combiner in accordance to the assignment; and combine the signals at the signal combiner.
7. The logic of claim 6 , operable to determine whether the signal comprises a voice signal in accordance with the content by: generating a feature vector for the signal, the feature vector describing the content associated with the signal; comparing the feature vector to a voice signal vector describing a typical voice signal; and determining whether the signal comprises a voice signal in accordance with the comparison.
8. The logic of claim 6 , operable to determine whether the signal comprises a voice signal in accordance with the content by: identifying a frequency spectrum associated with the signal; and determining whether the signal comprises a voice signal in accordance with the frequency spectrum.
9. The logic of claim 6 , operable to determine whether the signal comprises a voice signal in accordance with the content by determining whether the signal comprises a voice signal in accordance with the content at a speech recognition module.
10. The logic of claim 6 , operable to send the signals to the signal combiner in accordance with the determination of whether the signal comprises a voice signal by: sending the signal to the signal combiner if the signal comprises a voice signal; and blocking the signal if the signal comprises another type of signal.
11. A system for combining a plurality of signals, comprising: a speech recognition module operable to: receive a plurality of signals from a plurality of communication devices, each signal received from a communication device, each signal associated with a content describing the signal; and repeat the following for each signal of the plurality of signals: examine the content associated with a signal; and determine whether the signal comprises a voice signal in accordance with the content; a weighting module coupled to the speech recognition module and operable to transmit each signal in accordance with the determination of whether the signal comprises a voice signal by assigning a higher weight to the signal if the signal comprises a voice signal, assigning a lower weight to the signal if the signal comprises another type of signal, and transmitting the signal in accordance to the assignment; and a signal combiner coupled to the weighting module and operable to: receive the transmitted signals; and combine the signals.
12. The system of claim 11 , further comprising a vector generator operable to generate a feature vector for the signal, the feature vector describing the content associated with the signal, the speech recognition module being operable to determine whether the signal comprises a voice signal in accordance with the content by: comparing the feature vector to a voice signal vector describing a typical voice signal; and determining whether the signal comprises a voice signal in accordance with the comparison.
13. The system of claim 11 , wherein the speech recognition module is operable to determine whether the signal comprises a voice signal in accordance with the content by: identifying a frequency spectrum associated with the signal; and determining whether the signal comprises a voice signal in accordance with the frequency spectrum.
14. The system of claim 11 , wherein the weighting module comprises a switch operable to send the signals to the signal combiner in accordance with the determination of whether the signal comprises a voice signal by: sending the signal to the signal combiner if the signal comprises a voice signal; and blocking the signal if the signal comprises another type of signal.
15. A system for combining a plurality of signals, comprising: means for receiving a plurality of signals from a plurality of communication devices, each signal received from a communication device, each signal associated with a content describing the signal; means for repeating the following for each signal of the plurality of signals: examining the content associated with a signal; determining whether the signal comprises a voice signal in accordance with the content; and sending the signal to a signal combiner in accordance with the determination of whether the signal comprises a voice signal by assigning a higher weight to the signal if the signal comprises a voice signal, assigning a lower weight to the signal if the signal comprises another type of signal, and sending the signal to the signal combiner in accordance to the assignment; and means for combining the signals at the signal combiner.
16. A method for combining a plurality of signals, comprising: receiving a plurality of signals from a plurality of communication devices, each signal received from a communication device, each signal associated with a content describing the signal, and repeating the following for each signal of the plurality of signals: examining the content associated with a signal and determining whether the signal comprises a voice signal at a speech recognition module in accordance with the content by: generating a feature vector for the signal, the feature vector describing the content associated with the signal, comparing the feature vector to a voice signal vector describing a typical voice signal, and determining whether the signal comprises a voice signal in accordance with the comparison; and identifying a frequency spectrum associated with the signal, and determining whether the signal comprises a voice signal in accordance with the frequency spectrum; and sending the signal to a signal combiner in accordance with the determination of whether the signal comprises a voice signal by: assigning a higher weight to the signal if the signal comprises a voice signal, assigning a lower weight to the signal if the signal comprises another type of signal, and sending the signal to the signal combiner in accordance to the assignment; and sending the signal to the signal combiner if the signal comprises a voice signal, and blocking the signal if the signal comprises another type of signal; and combining the signals at the signal combiner.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 13, 2003
May 6, 2008
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.